Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance
Grain yield is increasingly affected by climate factors such as drought and heat. To develop resilient and high-yielding cultivars, high-throughput phenotyping (HTP) techniques are essential for precise decisions in wheat breeding. The ability of unmanned aerial vehicle (UAV)-based multispectral ima...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/12/2338 |
| _version_ | 1827689703271301120 |
|---|---|
| author | Shuaipeng Fei Muhammad Adeel Hassan Zhonghu He Zhen Chen Meiyan Shu Jiankang Wang Changchun Li Yonggui Xiao |
| author_facet | Shuaipeng Fei Muhammad Adeel Hassan Zhonghu He Zhen Chen Meiyan Shu Jiankang Wang Changchun Li Yonggui Xiao |
| author_sort | Shuaipeng Fei |
| collection | DOAJ |
| description | Grain yield is increasingly affected by climate factors such as drought and heat. To develop resilient and high-yielding cultivars, high-throughput phenotyping (HTP) techniques are essential for precise decisions in wheat breeding. The ability of unmanned aerial vehicle (UAV)-based multispectral imaging and ensemble learning methods to increase the accuracy of grain yield prediction in practical breeding work is evaluated in this study. For this, 211 winter wheat genotypes were planted under full and limited irrigation treatments, and multispectral data were collected at heading, flowering, early grain filling (EGF), and mid-grain filling (MGF) stages. Twenty multispectral vegetation indices (VIs) were estimated, and VIs with heritability greater than 0.5 were selected to evaluate the models across the growth stages under both irrigation treatments. A framework for ensemble learning was developed by combining multiple base models such as random forest (RF), support vector machine (SVM), Gaussian process (GP), and ridge regression (RR). The <i>R</i><sup>2</sup> values between VIs and grain yield for individual base models were ranged from 0.468 to 0.580 and 0.537 to 0.598 for grain yield prediction in full and limited irrigation treatments across growth stages, respectively. The prediction results of ensemble models were ranged from 0.491 to 0.616 and 0.560 to 0.616 under full and limited irrigation treatments respectively, and were higher than that of the corresponding base learners. Moreover, the grain yield prediction results were observed high at mid grain filling stage under both full (<i>R</i><sup>2</sup> = 0.625) and limited (<i>R</i><sup>2</sup> = 0.628) irrigation treatments through ensemble learning based stacking of four base learners. Further improvements in ensemble learning models can accelerate the use of UAV-based multispectral data for accurate predictions of complex traits like grain yield in wheat. |
| first_indexed | 2024-03-10T10:24:17Z |
| format | Article |
| id | doaj.art-4a0d254adae94f17bf5fa4150a5c5310 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T10:24:17Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4a0d254adae94f17bf5fa4150a5c53102023-11-22T00:09:57ZengMDPI AGRemote Sensing2072-42922021-06-011312233810.3390/rs13122338Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral ReflectanceShuaipeng Fei0Muhammad Adeel Hassan1Zhonghu He2Zhen Chen3Meiyan Shu4Jiankang Wang5Changchun Li6Yonggui Xiao7School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454003, ChinaNational Wheat Improvement Centre, Institute of Crop Sciences, Chinese Academy of Agricultural Sciences (CAAS), Beijing 100081, ChinaNational Wheat Improvement Centre, Institute of Crop Sciences, Chinese Academy of Agricultural Sciences (CAAS), Beijing 100081, ChinaFarmland Irrigation Research Institute, Chinese Academy of Agricultural Sciences (CAAS), Xinxiang 453002, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing 100193, ChinaCentre for Crop Genomics & Molecular Design, Institute of Crop Sciences, Chinese Academy of Agricultural Sciences (CAAS), Beijing 100081, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454003, ChinaNational Wheat Improvement Centre, Institute of Crop Sciences, Chinese Academy of Agricultural Sciences (CAAS), Beijing 100081, ChinaGrain yield is increasingly affected by climate factors such as drought and heat. To develop resilient and high-yielding cultivars, high-throughput phenotyping (HTP) techniques are essential for precise decisions in wheat breeding. The ability of unmanned aerial vehicle (UAV)-based multispectral imaging and ensemble learning methods to increase the accuracy of grain yield prediction in practical breeding work is evaluated in this study. For this, 211 winter wheat genotypes were planted under full and limited irrigation treatments, and multispectral data were collected at heading, flowering, early grain filling (EGF), and mid-grain filling (MGF) stages. Twenty multispectral vegetation indices (VIs) were estimated, and VIs with heritability greater than 0.5 were selected to evaluate the models across the growth stages under both irrigation treatments. A framework for ensemble learning was developed by combining multiple base models such as random forest (RF), support vector machine (SVM), Gaussian process (GP), and ridge regression (RR). The <i>R</i><sup>2</sup> values between VIs and grain yield for individual base models were ranged from 0.468 to 0.580 and 0.537 to 0.598 for grain yield prediction in full and limited irrigation treatments across growth stages, respectively. The prediction results of ensemble models were ranged from 0.491 to 0.616 and 0.560 to 0.616 under full and limited irrigation treatments respectively, and were higher than that of the corresponding base learners. Moreover, the grain yield prediction results were observed high at mid grain filling stage under both full (<i>R</i><sup>2</sup> = 0.625) and limited (<i>R</i><sup>2</sup> = 0.628) irrigation treatments through ensemble learning based stacking of four base learners. Further improvements in ensemble learning models can accelerate the use of UAV-based multispectral data for accurate predictions of complex traits like grain yield in wheat.https://www.mdpi.com/2072-4292/13/12/2338ensemble learninggrain yieldremote sensingmultispectral vegetation indicesbread wheatunmanned aerial vehicle |
| spellingShingle | Shuaipeng Fei Muhammad Adeel Hassan Zhonghu He Zhen Chen Meiyan Shu Jiankang Wang Changchun Li Yonggui Xiao Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance Remote Sensing ensemble learning grain yield remote sensing multispectral vegetation indices bread wheat unmanned aerial vehicle |
| title | Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance |
| title_full | Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance |
| title_fullStr | Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance |
| title_full_unstemmed | Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance |
| title_short | Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance |
| title_sort | assessment of ensemble learning to predict wheat grain yield based on uav multispectral reflectance |
| topic | ensemble learning grain yield remote sensing multispectral vegetation indices bread wheat unmanned aerial vehicle |
| url | https://www.mdpi.com/2072-4292/13/12/2338 |
| work_keys_str_mv | AT shuaipengfei assessmentofensemblelearningtopredictwheatgrainyieldbasedonuavmultispectralreflectance AT muhammadadeelhassan assessmentofensemblelearningtopredictwheatgrainyieldbasedonuavmultispectralreflectance AT zhonghuhe assessmentofensemblelearningtopredictwheatgrainyieldbasedonuavmultispectralreflectance AT zhenchen assessmentofensemblelearningtopredictwheatgrainyieldbasedonuavmultispectralreflectance AT meiyanshu assessmentofensemblelearningtopredictwheatgrainyieldbasedonuavmultispectralreflectance AT jiankangwang assessmentofensemblelearningtopredictwheatgrainyieldbasedonuavmultispectralreflectance AT changchunli assessmentofensemblelearningtopredictwheatgrainyieldbasedonuavmultispectralreflectance AT yongguixiao assessmentofensemblelearningtopredictwheatgrainyieldbasedonuavmultispectralreflectance |